Discover Skills | Humans to Know

positioning-critic

Competitive-differentiation reviewer that refuses to accept "the user wants this" as sufficient. Demands the plan say why a real customer would choose it over every alternative, including doing nothing — voice of a positioning strategist who has watched well-liked products lose to a clearer story. Use at any product checkpoint — plan, roadmap, go-to-market framing — when nobody can say why users would switch or pay, the competitive landscape is unaddressed, or "no one else does this" is asserted without checking: "why us, why this, why now?"

Strategy

personafy

Build a new opinionated advisor-persona skill — a reviewer "lens" like crusty-old-engineer, modeled on a real person or archetype. Mines the subject's authentic voice, defines its one load-bearing question, drafts it to the family template, and proves it steers a live session before publishing to a skills bundle. Use when creating or authoring a persona/advisor skill, adding a sibling to the crusty-old-engineer family, or turning a person's real direction style into a reusable reviewer skill. Also triggers on "personafy" / "personify".

UX Research

outcomist

Outcome-clarity reviewer that asks whether you have defined what you're trying to achieve and validated that the problem is real. Catches people BEFORE they build — the moment between "I should build X" and actually building it. Use when a build is starting without a validated problem or a plain-language definition of what success looks like.

Developer Tools

outcome-cartographer

Outcome-validity reviewer that refuses to count shipped work as progress until it maps to a measurable change in behavior. Hunts the gap between "we shipped it" and "we moved the number" — the output mistaken for an outcome. Use at any product checkpoint — plan, roadmap, PRD, ship review — when deliverables carry no metric, "done" is confused with "worked," or nobody can say how success will be measured: "what measurable outcome defines success, and how will we know we moved it?"

Strategy

monitor

Run a bounded, self-checking polling loop (sleep -> check -> decide, repeat) WITHOUT ENDING THE TURN. The turn ends only when the watched thing is done, has failed, or genuinely needs the user's attention — which is what makes Amplifier's end-of-turn notification fire correctly and honestly. Primarily invoked explicitly via `/monitor <thing to watch>`, e.g. `/monitor the CI run for PR 412, check every 2m, stop after 1h`. May also be self-invoked in the rare case you are about to tell the user "I'll keep working and let you know" for something with a genuinely checkable, bounded condition — see

Developer Tools

mass-change

Research and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.

AI Agents

intent-keeper

Goal-clarity reviewer that refuses to judge a solution until the intent behind it is pinned. A patient interrogator of "why are we doing this?", hunting goal drift — the deliverable quietly replacing the goal. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when the build has wandered from the brief or nobody can say in one sentence what success looks like: "is this still the real goal?"

UI Design

image-vision

Analyze images using LLM vision APIs (Anthropic Claude, OpenAI GPT-4, Google Gemini, Azure OpenAI). Use when a task requires understanding image content, describing visual elements, answering questions about images, comparing images, or extracting text from images (OCR). Provides ready-to-use scripts.

Cloud Platforms

engineering-patterns

Use for tool/service work: CLI packaging, installers, config/state, HTTP, auth/TLS, file IPC, plugins, instance storage, containers, React MFE, Graph, self-update, tool leverage.

Containers

crusty-old-engineer

Curmudgeonly engineering advisor: grounded skepticism and evidence-linked judgment on architecture, legacy refactors, and tooling choices. Voice of a senior systems engineer who has reviewed too many designs to be impressed but still cares about correctness. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when weighing consequences, hidden costs, or failure modes of a choice, or for broad "how should I start?" questions: "what will this cost us later?"

UI Design

cranky-old-sam

Simplicity-obsessed reviewer that interrogates complexity and insists on the minimal viable design. Voice of a senior engineer who treats every unnecessary layer as a personal affront. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when anything looks more complex than the problem needs: a speculative idea, an abstraction, a layer, an over-built fix. The worry: "do we actually need this, or can it be deleted?"

UI Design

councilify

Build a NEW complete "council" for a domain — a panel of orthogonal review lenses that fan out cold, debate to consensus, and return a synthesized verdict with recorded dissent, exactly like /council and /design-council. Identifies the distinct lenses a domain needs (one load-bearing question each, mined from real archetypes — not invented), reuses existing lenses, and builds only the genuinely-missing ones (persona SKILLs via personafy, or agents when the role is an active builder). Use when creating a council, standing up a review panel for a domain (product, security, performance, data), or

Application Security

council

Convene the persona panel — six orthogonal review lenses — on a target. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.

UX Research

council-here

Convene the persona panel on the CURRENT conversation — the plan, design, or decision built in this session. The INLINE counterpart to /council (which forks isolated and cannot see the chat). Use when you want the council to critique what we're working on right now.

UX Research

code-review

Review changed code for reuse, quality, and efficiency, then fix any issues found.

Testing

bet-sizer

Delivery-risk reviewer that sizes a plan's investment against the team's real confidence it will land. Voice of a delivery lead who has watched too many "should be straightforward" estimates blow up on the one unknown nobody named. Use at any product checkpoint — plan, roadmap, investment/sequencing decision — when a timeline carries more confidence than the team has, the riskiest unknown is buried, or nobody has said what would make this slip: "is the investment sized to our confidence?"

Strategy

adapt-skill

Adapt a skill written for another AI assistant (Claude Code, Cursor, etc.) into a proper Amplifier SKILL.md. Use when the user wants to adapt a skill, port a skill, convert a skill to amplifier, translate a skill, or has a SKILL.md from another platform they want to bring into Amplifier.

AI Agents

ten-lane-highway

Become the Highway Manager: drive many parallel /goal lanes continuously toward a defined outcome, refilling lanes on every wake so none sit idle. Use when the user wants continuous parallel throughput toward an outcome: "run the highway", "/highway", "10-lane highway", "keep N lanes full", "keep re-feeding lanes as they drain", "drive this for me in parallel", "do them all and monitor", "keep the lanes full", "work the whole list in parallel until done". NOT for a one-shot batch that launches once and drains together — use goal-batch. NOT for bounded edits that each end in their own PR — use

Developer Tools

goalify

Compose and lint a /goal stop-condition from the current conversation, catching known termination-failure patterns before showing it to the user. Use when the user wants to turn the current task into a /goal loop, asks to "goalify this", wants a stop condition for autonomous work, says "write a goal condition", "make this a /goal", "turn this into a goal", or asks for help wording a condition for /goal.

Developer Tools

goal-batch

Batch independent work into isolated /goal lanes — one worktree, branch, and tmux session each — get your approval, then verify and merge every lane yourself. Use when work decomposes into pieces that can run at the same time: "run these in parallel", "goal-batch", "launch lanes for these", "work these N tasks simultaneously", "batch these as goals". Nothing launches until you've seen the lane split and said go, and this is NOT fire-and-forget: the orchestrating session re-runs the full suite after every merge and never accepts a lane's own claim that it finished. NOT for bounded edits that ea

Testing

amplifier-config

Explain, inspect, troubleshoot, and safely modify Amplifier CLI configuration — providers, settings scopes, bundles, routing, skills, and source overrides. Use when someone describes desired Amplifier CLI behavior and needs effective-value provenance, a safe change plan, implementation, or outcome-based verification.

Testing

pre-push-review

Pre-PR self-review using the same criteria as the automated review-pr-opened GitHub Action. Catches stale mock patch targets, dead imports with noqa suppressors, fixture env-var leaks, and silent ineffective patches BEFORE they are flagged by CI. Run before pushing any branch to a PR on microsoft/amplifier-resolve. Triggers on: "review before push", "pre-PR check", "self-review before pushing", "catch issues before CI", "is this ready to push".

Testing

pr-review

Local PR review in your session — exhaustive (5 independent review lenses with quality synthesis) or prompt-shot (single-pass five-check framework). No GitHub comment posted. Use when the user wants a local code review of a branch diff, staged changes, or PR before pushing/merging.

Testing

Newest skills

Newest skills